© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38527
    Prev
    Next
    INDEX
    Explanations

    terms of

    np_acts-logits-general · gemini-2.5-flash-lite

    hypertensive crisis, Python versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.54
    d
    0.46
     Contract
    0.44
     Casualty
    0.42
    Contract
    0.41
     Sight
    0.41
    Notably
    0.41
    ებული
    0.40
    H
    0.40
    v
    0.40
    POSITIVE LOGITS
     신청
    0.52
     rbuf
    0.52
     Yatha
    0.50
     మూడు
    0.50
    форм
    0.49
    leting
    0.49
     شاہ
    0.48
    యోగ
    0.47
     alleviating
    0.47
    켰
    0.47
    Activations Density 0.000%

    No Known Activations